distillery 0.2.7 → 0.2.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/distillery/document.rb +20 -7
- data/lib/distillery/version.rb +1 -1
- data/spec/acceptance_spec.rb +9 -0
- data/spec/fixtures/bilays.html +2811 -0
- data/spec/lib/distillery/document_spec.rb +0 -8
- metadata +21 -19
|
@@ -195,14 +195,6 @@ module Distillery
|
|
|
195
195
|
doc.search('.remove').should_not be_empty
|
|
196
196
|
end
|
|
197
197
|
|
|
198
|
-
it 'removes elements that have < 25 characters and (no images or > 2 images' do
|
|
199
|
-
doc = doc_with_top_scored_html_of("<div class='remove'><div>foo</div></div>", :clean_top_scoring_elements!)
|
|
200
|
-
doc.search('.remove').should be_empty
|
|
201
|
-
|
|
202
|
-
doc = doc_with_top_scored_html_of("<div class='remove'><div>foo <img><img><img></div></div>", :clean_top_scoring_elements!)
|
|
203
|
-
doc.search('.remove').should be_empty
|
|
204
|
-
end
|
|
205
|
-
|
|
206
198
|
it 'removes elements that have a weight of < 25 and link density > 0.2' do
|
|
207
199
|
doc = doc_with_top_scored_html_of("<div class='remove'><div>fffff<a>#{'b'*2}</a></div></div>", :clean_top_scoring_elements!)
|
|
208
200
|
doc.search('.remove').should be_empty
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: distillery
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.9
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,11 +9,11 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2011-
|
|
12
|
+
date: 2011-11-17 00:00:00.000000000Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: nokogiri
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &2152684340 !ruby/object:Gem::Requirement
|
|
17
17
|
none: false
|
|
18
18
|
requirements:
|
|
19
19
|
- - ! '>'
|
|
@@ -21,10 +21,10 @@ dependencies:
|
|
|
21
21
|
version: '1.0'
|
|
22
22
|
type: :runtime
|
|
23
23
|
prerelease: false
|
|
24
|
-
version_requirements: *
|
|
24
|
+
version_requirements: *2152684340
|
|
25
25
|
- !ruby/object:Gem::Dependency
|
|
26
26
|
name: slop
|
|
27
|
-
requirement: &
|
|
27
|
+
requirement: &2152683360 !ruby/object:Gem::Requirement
|
|
28
28
|
none: false
|
|
29
29
|
requirements:
|
|
30
30
|
- - ! '>'
|
|
@@ -32,10 +32,10 @@ dependencies:
|
|
|
32
32
|
version: '1.0'
|
|
33
33
|
type: :runtime
|
|
34
34
|
prerelease: false
|
|
35
|
-
version_requirements: *
|
|
35
|
+
version_requirements: *2152683360
|
|
36
36
|
- !ruby/object:Gem::Dependency
|
|
37
37
|
name: rspec
|
|
38
|
-
requirement: &
|
|
38
|
+
requirement: &2152682380 !ruby/object:Gem::Requirement
|
|
39
39
|
none: false
|
|
40
40
|
requirements:
|
|
41
41
|
- - ! '>'
|
|
@@ -43,10 +43,10 @@ dependencies:
|
|
|
43
43
|
version: '2.0'
|
|
44
44
|
type: :development
|
|
45
45
|
prerelease: false
|
|
46
|
-
version_requirements: *
|
|
46
|
+
version_requirements: *2152682380
|
|
47
47
|
- !ruby/object:Gem::Dependency
|
|
48
48
|
name: guard
|
|
49
|
-
requirement: &
|
|
49
|
+
requirement: &2152681520 !ruby/object:Gem::Requirement
|
|
50
50
|
none: false
|
|
51
51
|
requirements:
|
|
52
52
|
- - ! '>='
|
|
@@ -54,10 +54,10 @@ dependencies:
|
|
|
54
54
|
version: '0'
|
|
55
55
|
type: :development
|
|
56
56
|
prerelease: false
|
|
57
|
-
version_requirements: *
|
|
57
|
+
version_requirements: *2152681520
|
|
58
58
|
- !ruby/object:Gem::Dependency
|
|
59
59
|
name: guard-rspec
|
|
60
|
-
requirement: &
|
|
60
|
+
requirement: &2152680820 !ruby/object:Gem::Requirement
|
|
61
61
|
none: false
|
|
62
62
|
requirements:
|
|
63
63
|
- - ! '>='
|
|
@@ -65,10 +65,10 @@ dependencies:
|
|
|
65
65
|
version: '0'
|
|
66
66
|
type: :development
|
|
67
67
|
prerelease: false
|
|
68
|
-
version_requirements: *
|
|
68
|
+
version_requirements: *2152680820
|
|
69
69
|
- !ruby/object:Gem::Dependency
|
|
70
70
|
name: ruby-debug19
|
|
71
|
-
requirement: &
|
|
71
|
+
requirement: &2152680240 !ruby/object:Gem::Requirement
|
|
72
72
|
none: false
|
|
73
73
|
requirements:
|
|
74
74
|
- - ! '>='
|
|
@@ -76,10 +76,10 @@ dependencies:
|
|
|
76
76
|
version: '0'
|
|
77
77
|
type: :development
|
|
78
78
|
prerelease: false
|
|
79
|
-
version_requirements: *
|
|
79
|
+
version_requirements: *2152680240
|
|
80
80
|
- !ruby/object:Gem::Dependency
|
|
81
81
|
name: rb-fsevent
|
|
82
|
-
requirement: &
|
|
82
|
+
requirement: &2152679540 !ruby/object:Gem::Requirement
|
|
83
83
|
none: false
|
|
84
84
|
requirements:
|
|
85
85
|
- - ! '>='
|
|
@@ -87,10 +87,10 @@ dependencies:
|
|
|
87
87
|
version: '0'
|
|
88
88
|
type: :development
|
|
89
89
|
prerelease: false
|
|
90
|
-
version_requirements: *
|
|
90
|
+
version_requirements: *2152679540
|
|
91
91
|
- !ruby/object:Gem::Dependency
|
|
92
92
|
name: growl
|
|
93
|
-
requirement: &
|
|
93
|
+
requirement: &2152678080 !ruby/object:Gem::Requirement
|
|
94
94
|
none: false
|
|
95
95
|
requirements:
|
|
96
96
|
- - ! '>='
|
|
@@ -98,7 +98,7 @@ dependencies:
|
|
|
98
98
|
version: '0'
|
|
99
99
|
type: :development
|
|
100
100
|
prerelease: false
|
|
101
|
-
version_requirements: *
|
|
101
|
+
version_requirements: *2152678080
|
|
102
102
|
description: Distillery extracts the "content" portion out of an HTML document. It
|
|
103
103
|
applies heuristics based on element type, location, class/id name and other attributes
|
|
104
104
|
to try and find the content part of the HTML document and return it.
|
|
@@ -126,6 +126,7 @@ files:
|
|
|
126
126
|
- spec/fixtures/agave_cookies.html
|
|
127
127
|
- spec/fixtures/baked_ziti.html
|
|
128
128
|
- spec/fixtures/beef_jerkey.html
|
|
129
|
+
- spec/fixtures/bilays.html
|
|
129
130
|
- spec/fixtures/bourbon_balls.html
|
|
130
131
|
- spec/fixtures/bulgogi.html
|
|
131
132
|
- spec/fixtures/clams_and_linguini.html
|
|
@@ -163,7 +164,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
163
164
|
version: '0'
|
|
164
165
|
requirements: []
|
|
165
166
|
rubyforge_project: distillery
|
|
166
|
-
rubygems_version: 1.8.
|
|
167
|
+
rubygems_version: 1.8.10
|
|
167
168
|
signing_key:
|
|
168
169
|
specification_version: 3
|
|
169
170
|
summary: Extract the content portion of an HTML document.
|
|
@@ -173,6 +174,7 @@ test_files:
|
|
|
173
174
|
- spec/fixtures/agave_cookies.html
|
|
174
175
|
- spec/fixtures/baked_ziti.html
|
|
175
176
|
- spec/fixtures/beef_jerkey.html
|
|
177
|
+
- spec/fixtures/bilays.html
|
|
176
178
|
- spec/fixtures/bourbon_balls.html
|
|
177
179
|
- spec/fixtures/bulgogi.html
|
|
178
180
|
- spec/fixtures/clams_and_linguini.html
|